Story thread · 6 reports / 5 sources

Thinking Machines Lab Releases Inkling-Small: A 276B Total, 12B Active Open Weights Multimodal MoE Model

marktechpost.com · 9dShare

Inkling-Small matches Inkling at a quarter the size, and its NVFP4 checkpoint runs on one NVIDIA B300 GPU The post Thinking Machines Lab Releases Inkling-Small: A 276B Total, 12B Active Open Weights Multimodal MoE Model appeared first on MarkTechPost .

First report: Thinking Machines debuts Inkling Small open source AI model nearing performance of predecessor at about 1/4 size — venturebeat.com, 11d